Youshou Wu

Adaptive confidence transform based classifier combination for Chinese character recognition

Abstract Classifier combination is an effective way to improve recognition performance. However, in Chinese character recognition the extremely large number of categories results in several difficulties for the combination. In order to overcome these difficulties a novel combination method is presented in this paper. It consists of three main components: adaptive confidence transform (ACT), consensus theoretic combination and reliability based speedup scheme. ACT, which can estimate a posteriori probabilities from raw measurement values, is the focus of this paper. Experimental results show a significant reduction of error rates in both printed (PCCR) and handwritten Chinese character recognition (HCCR).

Description and recognition of form and automated form data entry

In this paper we present a form description method, in which frame lines are used to constitute a so-called frame template, which reflects the structure of a form either topologically or geometrically. Relevant item traversal algorithm is then proposed to locate and label forms items. We have also developed a robust and fast frame line detection method to make this form description practical for form recognition. Experimental results show our approach provides an effective way to convert printed forms into computerized format or collect information for database from printed forms.

Recognizing on-line handwritten Chinese character via FARG matching

The paper presents a novel method for online handwritten Chinese character recognition. In our method, each category of character is described by a fuzzy attributed relational graph (FARG). A relaxation algorithm is developed to match the input pattern with every FARG. For decision making, a similarity measure is established via statistical technique to calculate the matching degree between the input pattern and referenced FARG, according to which the recognition result is determined. The principle of our method makes it very robust against stroke connection and stroke order variation as well as stroke shape deformation. A database of 22530 samples collected from 6 subjects is used to test our recognition system which can recognize 3755 categories of Chinese characters. The result shows that our method is very effective: a top 1 recognition rate of 98.8% and a top 10 of 99.7% are reached.

A segmentation algorithm for handwritten Chinese character strings

A new algorithm for segmenting handwritten Chinese character strings is presented. This approach is based on a split-and-merge strategy by locating possible ligatures between Chinese characters and merging the over-split components. The strategy is proposed by considering the structural properties of Chinese character strings. To guarantee the accuracy of the above segmentation algorithm, a recognizer is involved in order to aid the segmentation process. A maximum a posteriori probability index is derived for joint optimization of the segmentation and recognition results, and a dynamic programming algorithm-a modified level-building algorithm-is used to optimize this index. The whole algorithm is applied to a Chinese bank check amount recognition task, and some promising experimental results are obtained.

Off-line handwritten Chinese character recognition based on crossing line feature

A new method to extract crossing line features for off-line handwritten Chinese character recognition is proposed in this paper. Firstly, the input pattern is nonlinearly normalized in order to compensate for shape variations. Secondly, the normalized pattern is separated into four subpatterns according to the four kinds of elementary strokes. Thirdly, the four subpatterns are uniformly divided into M/spl times/M cells respectively. In every cell, the crossing lines are counted. Then a 4M/sup 2/-dimensional feature vector is generated. An off-line handwritten Chinese character recognition system is built based on this feature. Our experiments have demonstrated the effectiveness of the method proposed in this paper.

Spatio-temporal unified model for on-line handwritten Chinese character recognition

This paper presents a novel spatio-temporal modeling method for on-line handwritten Chinese character recognition. In this method, a statistical structure model (SSM) is used to describe the structural feature of Chinese characters from a probabilistic aspect, and an improved hidden Markov model (PCHMM) is employed to capture temporal information contained in ink. These two models are combined closely leading to a powerful spatio-temporal unified model (STUM), which has shown strong description ability and resulted in superior performance in the experiments where traditional models such as HMM (Hidden Markov Model) and ARG (Attributed Relational Graph) are also introduced and compared.

Realization of a high-performance bilingual Chinese-English OCR system

This paper focuses on the realization of a bilingual Chinese-English OCR system. First, the Twice-Segment Algorithm is used for segmentation of documents with Chinese and English characters mixed. Then the comprehensive recognition method is employed to improve the robustness of Chinese character recognition. A new measurement of robustness of OCR recognition performance is also put forward here. Finally, exciting experimental results are given.

A New Nonlinear Shape Normalization Method for Off-line Handwritten Chinese Character Recognition

How to correct the shape variations of handwritten Chinese characters is very important in off-line handwritten Chinese character recognition. In order to get rid of shape variations and reduce within-category variances directly from handwritten Chinese character image, a new nonlinear shape normalization method is proposed in this paper. In this new method, both of the stroke pixels and the background pixels are assigned with different feature densities. In addition, the feature density is local and two-dimensional. It is more reasonable and more effective than other nonlinear shape normalization methods. Its effectiveness has been demonstrated by our experiments.

Evaluation and Application of Recognition Confidence in OCR

Recognition confidence plays an important role in the selection of rejection threshold and the combination of multiple classifiers. In this paper, we first present a systematic theory on classifiers confidence, which includes the definition, the concept of generalized confidence, optimal rejection theorem and the relationship between confidence value and recognition rate. Then we propose a method for the evaluation of recognition confidence. The theory and method are strongly supported by the practice in handwritten numeral recognition and off-line handwritten Chinese character recognition.

Combinatorial Coarse Classification Method for OLCCR

This paper presents a new coarse classification method based on combination of two independent approaches for on-line Chinese character recognition (OLCCR). Through introducing a feedback control provided by the fine classifier, we are able to reach a good trade-off betweenprecision and speed. In the paper, we make some theoretical analysis on the form of combination, and compare it with competing methods. Both theoretical analysis and experimental results show that our method has the characteristics of high correct rate, good recognition speed, being easy to control and adaptable to various needs for practical application through parameter adjustment.